© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37763
    Prev
    Next
    INDEX
    Explanations

    forecast and projections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ī项
    -0.09
    åŃĺéĩı
    -0.09
    å¼Ĥåij³
    -0.09
    åįĩåįİ
    -0.08
    åıĮèĦļ
    -0.08
    :///
    -0.08
    /to
    -0.08
    åIJ¦
    -0.08
    uous
    -0.08
    ilon
    -0.08
    POSITIVE LOGITS
    ì¹ĺ
    0.09
     cle
    0.09
    æijĺç¼ĸ
    0.09
    виÑĤ
    0.09
    å·²ä¹ħ
    0.09
    å·²ä¹ħçļĦ
    0.09
    ç¾İ人
    0.09
    å½¢åĬ¿
    0.08
    ä¸įå¾Ĺä¸į
    0.08
    cle
    0.08
    Activations Density 0.023%

    No Known Activations